{"created":"2025-01-19T00:59:35.479984+00:00","updated":"2025-01-19T23:26:42.249592+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00194544","sets":["1164:3980:9689:9690"]},"path":["9690"],"owner":"44499","recid":"194544","title":["マイクロフォンを用いた鉄道乗車位置推定手法の設計と評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-02-21"},"_buckets":{"deposit":"f1d9f1c5-7e18-4455-aece-9d72bd930458"},"_deposit":{"id":"194544","pid":{"type":"depid","value":"194544","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"マイクロフォンを用いた鉄道乗車位置推定手法の設計と評価","author_link":["460680","460679","460681","460682"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"マイクロフォンを用いた鉄道乗車位置推定手法の設計と評価"}]},"item_type_id":"4","publish_date":"2019-02-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"九州大学大学院システム情報科学研究院"},{"subitem_text_value":"九州大学大学院システム情報科学研究院"},{"subitem_text_value":"関西大学総合情報学部"},{"subitem_text_value":"九州大学大学院システム情報科学研究院"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"ISEE, Kyushu University","subitem_text_language":"en"},{"subitem_text_value":"ISEE, Kyushu University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Informatics, Kansai University","subitem_text_language":"en"},{"subitem_text_value":"ISEE, Kyushu University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/194544/files/IPSJ-ITS19076005.pdf","label":"IPSJ-ITS19076005.pdf"},"date":[{"dateType":"Available","dateValue":"2021-02-21"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ITS19076005.pdf","filesize":[{"value":"813.0 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"37"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"c8011c8a-5a6f-4efa-b430-ec36ede9427d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"佐藤, 孝嗣"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"石田, 繁巳"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"田頭, 茂明"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"福田, 晃"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11515904","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8965","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本稿ではマイクロフォンを用いた鉄道におけるユーザの乗車位置推定手法を提案する．提案手法ではプラットフォーム上に立つユーザの持つ携帯端末を用いて列車到着時の音声を取得し，車輪が線路の継ぎ目の上を通過するときに発生するジョイント音と呼ばれる音を利用して乗車位置を車両単位で推定する．本手法は学習ベースの手法でジョイント音を検知するジョイント音検知ブロックと検知されたジョイント音の中から車体構造を利用して雑音除去を行い，乗車位置推定を行う乗車位置推定ブロックで構成される．ジョイント音検知ブロックでは，音声の周波数成分を基に特徴量を設計し，ロジスティック回帰分析を行い，各時刻でのジョイント音が発生していると思われる確率を計算し，ジョイント音の発生時刻を検知する．乗車位置推定ブロックでは，列車の車両構造を利用して雑音除去と乗車位置推定を行う．車両連結部の 4 つの車輪の間隔の比が既知であることから，等速度，等加速度においてジョイント音の発生間隔のモデルを作成し，そのモデルを利用して乗車位置を車両単位で推定する．提案手法の評価を交差検証で行った結果，推定精度が学習データによって大きく影響を受けることがわかった．そのため，学習データを限定して評価を行い，最高で平均推定誤差 0.91 車両で乗車位置を推定できることを確認した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告高度交通システムとスマートコミュニティ（ITS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-02-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicVolumeNumber":"2019-ITS-76"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":194544,"links":{}}